From Claude Code in your terminal to a live site

Claude Code is different from the chat tools in one way that changes the whole deploy story: it writes files directly into your project folder. There is no artifact to export, no preview to escape, no download step. When a session ends, the site is already on your disk, complete. What is missing is the last hop, from a folder on your machine to a URL the world can open. This is the deep dive on that hop: the two ways to make Claude Code deploy its own work, which project types survive the trip, and the loop that turns your terminal into the only tool you touch.

Where a Claude Code session actually leaves you

At the end of a Claude Code session you have a project directory with real files in it: HTML, a stylesheet, scripts, maybe a dist folder if you asked for a build. You can run a local preview and it looks finished. It is finished, as code. But a local preview is visible to exactly one computer on earth, and a folder is a website the way a printed manuscript is a published book. The gap is hosting, and the usual way to cross it, push to GitHub, sign up for a separate deploy platform, wire up a pipeline, is a second job the agent just spent an hour helping you avoid.

The better move is to make the agent close its own loop. Claude Code is both a coding agent and a shell, so it is capable of doing the deploy itself. There are two routes, and both end in a live URL printed in the same terminal window where the code was written.

Route one: MCP, the smooth road

Claude Code is a native MCP client, which means it can connect to a deploy server and gain deploy actions as first-class capabilities. Connecting VibeDeploy is a single command, run once:

claude mcp add --transport http vibedeploy https://mcp.vibedeploy.be/mcp

All the flags go before the server name. Add --scope user to make the server available in every project on your machine; without it, the server registers for the current project only. Stay on the http transport, since the older SSE transport is deprecated.

After that, start a 14-day free trial (no card), run the /mcp command inside a session to authorise once in a browser window, and that is the last time you leave the terminal. From then on the deploy is a sentence: "deploy this site to VibeDeploy." The agent calls the deploy tool, uploads the files, and prints a live URL of the form name.vibedeploy.be. The full setup, including the shared-repo case, is on the Claude Code guide.

If your project is a shared repository, you can commit the connection so it travels with the code rather than living on one machine. Drop a .mcp.json at the repo root:

{
  "mcpServers": {
    "vibedeploy": { "url": "https://mcp.vibedeploy.be/mcp" }
  }
}

Now everyone who opens the project in Claude Code gets the same deploy target and authorises with their own account. The deploy capability becomes part of the repo, not a per-developer chore.

Route two: the magic file, no MCP at all

MCP is the comfortable path, but it is genuinely optional, because Claude Code can run shell commands. That means it can talk to VibeDeploy's plain HTTP deploy API directly. Export the magic deploy file from your dashboard, drop it in the project folder, and tell the agent to deploy. It reads the instructions, packages the files, and POSTs them to the API itself. No MCP setup, no extra command, just a file the agent knows how to follow.

This route matters in two situations: a locked-down environment where you would rather not register an MCP server, and a first deploy where you want the shortest possible path before committing to a setup. The mechanics of the magic file are the same instruction-file pattern used across the chat tools, and it is the fallback that guarantees Claude Code can always ship, whatever the environment.

Which projects deploy cleanly

VibeDeploy serves static and single-page-app output, so the question is what your Claude Code project compiles down to.

• Plain HTML, CSS and JavaScript. Deploys as-is. Nothing to build.
• Vite, Astro, or a static Next.js export. Run the build, and the dist (or out) folder is what deploys. Ask Claude Code to run the build first; it knows the command.
• A single-page React or Vue app. Fine, because the whole app compiles to static files served to the browser.

The one class that does not fit is anything needing a running server: server-side rendering, API routes, a live database connection. Those need a server host, which is a different model. If Claude Code built you an SSR app, that is the signal to keep it on a server platform rather than a static host. For the many projects that are static, though, the deploy is genuinely one sentence.

The redeploy loop is the real win

The first deploy is nice. The second one is the point. Once the connection exists, your workflow collapses to a single window: describe a change, Claude Code edits the files, Claude Code redeploys, the URL serves the new version. No context switch to a browser, no commit-and-wait, no separate deploy dashboard. Because VibeDeploy's pricing is flat per plan rather than metered, letting the agent redeploy twenty times in an afternoon costs exactly nothing extra, so there is no reason to batch changes or hesitate. Every deploy is also recorded, so a revision that breaks something rolls back in one action.

This is the same iteration loop that makes the chat tools productive, but tighter, because the terminal never has to hand control to anything else. The agent that wrote the line also shipped it.

Putting it on your own domain

A name.vibedeploy.be subdomain is right for testing. For anything public, attach your domain: add it in site settings and point a CNAME at VibeDeploy. SSL provisions automatically, usually within 60 seconds, and until it resolves the site stays reachable on its subdomain. From then on the custom domain serves every redeploy the agent makes, with no further DNS work.

What it costs, and the neighbouring case

The 14-day trial covers a full site with a custom domain, so the entire flow above is free to try end to end. After that, plans start at 15 euro per month including Belgian VAT, flat, with custom domains and SSL on every plan; the tiers are on the pricing page. If your Claude work happens in the chat rather than the terminal, the single-file artifact path is its own guide, Claude artifacts to your own domain, and the broader map of deploying any AI-built site is the pillar at how to deploy AI-built websites in 2026. But if you live in Claude Code, the shape of the answer is simple: the terminal that built the site can be the terminal that runs it, and the round trip from idea to live URL never leaves the window.